San Francisco · Google · China · Germany · MIT Technology Review
This AI entrepreneur is developing agents that can plan ahead for the unexpected
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Danijar Hafner’s office in San Francisco’s SoMa district sits mostly empty.
Key facts
- His Dreamer 2 was the first agent to hit human-level performance playing Atari 2600 games using a world model
- In 2015, as a second-year undergraduate studying engineering at Hasso Plattner Institute in Potsdam, he won a role as a student researcher at Google Brain
- Dreamer 3 was the first one to solve the Minecraft Diamond challenge—successfully mining in-game gems on its own
- While Hafner, 31, won’t say too much about his new venture yet, he describes it as a continuation of his longtime work to enable AI to navigate environments it has not encountered in training
Summary
His brand-new startup is still in stealth mode and doesn’t even have its name on the door. While Hafner, 31, won’t say too much about his new venture yet, he describes it as a continuation of his longtime work to enable AI to navigate environments it has not encountered in training. To achieve this, Hafner relies on something called model-based reinforcement learning. He develops world models—AI models designed to emulate physical reality—and trains agents within them. “I get to interact with a lot of smart people in research at Google, and he easily sits in the top half of 1%.” Unlike other efforts, Hafner’s technique enables agents and the robots they control to execute massively complicated tasks without the real-world trial-and-error training that’s traditionally been used in robotics.